Related papers: Learning sound representations using trainable COP…

This paper presents a new approach to phoneme recognition using nonsequential sub--phoneme units. These units are called acoustic events and are phonologically meaningful as well as recognizable from speech signals. Acoustic events form a…

Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Feature extraction plays an important role as a front-end processing block in speaker identification (SI) process. Most of the SI systems utilize like Mel-Frequency Cepstral Coefficients (MFCC), Perceptual Linear Prediction (PLP), Linear…

The capability for environmental sound recognition (ESR) can determine the fitness of individuals in a way to avoid dangers or pursue opportunities when critical sound events occur. It still remains mysterious about the fundamental…

The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature…

We present a novel method for extracting neural embeddings that model the background acoustics of a speech signal. The extracted embeddings are used to estimate specific parameters related to the background acoustic properties of the signal…

While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio…

In this paper, we propose a new Sound Event Classification (SEC) method which is inspired in recent works for out-of-distribution detection. In our method, we analyse all the activations of a generic CNN in order to produce feature…

We propose a novel approach for spoofed speech characterization through explainable probabilistic attribute embeddings. In contrast to high-dimensional raw embeddings extracted from a spoofing countermeasure (CM) whose dimensions are not…

Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance…

With ever-increasing number of car-mounted electric devices and their complexity, audio classification is increasingly important for the automotive industry as a fundamental tool for human-device interactions. Existing approaches for audio…

Music tag words that describe music audio by text have different levels of abstraction. Taking this issue into account, we propose a music classification approach that aggregates multi-level and multi-scale features using pre-trained…

In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE) equipped with self-attention as a generative model to…

Accurate state estimation requires careful consideration of uncertainty surrounding the process and measurement models; these characteristics are usually not well-known and need an experienced designer to select the covariance matrices. An…

Realistic recordings of soundscapes often have multiple sound events co-occurring, such as car horns, engine and human voices. Sound event retrieval is a type of content-based search aiming at finding audio samples, similar to an audio…

The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive the dynamic scene, which is significant and imperative in many vision tasks. Most of existing methods only consider visual cues, while…

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

Distinct striation patterns are observed in the spectrograms of speech and music. This motivated us to propose three novel time-frequency features for speech-music classification. These features are extracted in two stages. First, a preset…

Separating signals from an additive mixture may be an unnecessarily hard problem when one is only interested in specific properties of a given signal. In this work, we tackle simpler "statistical component separation" problems that focus on…